© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 21-LLAMASCOPE-RES-32K
    11. 15388
    Prev
    Next
    INDEX
    Explanations

    instances of destruction and the aftermath of disasters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     drowning
    -0.15
    žÃŃ
    -0.15
    256
    -0.14
    éģĭåĭķ
    -0.14
     Forgotten
    -0.14
     ÙħØ´Ú©
    -0.13
    ÑŁ
    -0.13
    362
    -0.13
    éĻ°
    -0.13
    εÏģÏĮ
    -0.13
    POSITIVE LOGITS
     damage
    0.40
     destruction
    0.37
     destroyed
    0.35
     rubble
    0.34
     damaged
    0.32
     Damage
    0.32
     debris
    0.32
    destroy
    0.31
    damage
    0.31
     DAMAGE
    0.30
    Activations Density 0.276%

    No Known Activations